Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

Dataset: The Pile

Neuron 2740 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0096. Min Act: -0.0000

Data Index: 1477023 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0095. Min Act: -0.0000

Data Index: 125951 (The Pile)

Max Activating Token Index: 998

Text #2

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0092. Min Act: -0.0000

Data Index: 324468 (The Pile)

Max Activating Token Index: 980

Text #3

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0093. Min Act: -0.0000

Data Index: 1054851 (The Pile)

Max Activating Token Index: 1006

Text #4

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0090. Min Act: -0.0000

Data Index: 508409 (The Pile)

Max Activating Token Index: 966

Text #5

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0089. Min Act: -0.0000

Data Index: 210092 (The Pile)

Max Activating Token Index: 1010

Text #6

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0087. Min Act: -0.0000

Data Index: 54046 (The Pile)

Max Activating Token Index: 1006

Text #7

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0087. Min Act: 0.0000

Data Index: 874770 (The Pile)

Max Activating Token Index: 990

Text #8

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0087. Min Act: -0.0000

Data Index: 143558 (The Pile)

Max Activating Token Index: 1021

Text #9

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0087. Min Act: -0.0000

Data Index: 273865 (The Pile)

Max Activating Token Index: 1012

Text #10

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0087. Min Act: -0.0000

Data Index: 1081462 (The Pile)

Max Activating Token Index: 982

Text #11

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0084. Min Act: -0.0000

Data Index: 359801 (The Pile)

Max Activating Token Index: 1000

Text #12

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0086. Min Act: -0.0000

Data Index: 165912 (The Pile)

Max Activating Token Index: 994

Text #13

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0086. Min Act: 0.0000

Data Index: 1236904 (The Pile)

Max Activating Token Index: 1022

Text #14

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0086. Min Act: -0.0000

Data Index: 1431491 (The Pile)

Max Activating Token Index: 987

Text #15

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0083. Min Act: -0.0000

Data Index: 992997 (The Pile)

Max Activating Token Index: 953

Text #16

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0085. Min Act: -0.0000

Data Index: 1541899 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0085. Min Act: -0.0000

Data Index: 277354 (The Pile)

Max Activating Token Index: 988

Text #18

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0083. Min Act: -0.0000

Data Index: 1326007 (The Pile)

Max Activating Token Index: 967

Text #19

Max Range: 0.0096. Min Range: -0.0096

Max Act: 0.0085. Min Act: -0.0000

Data Index: 707193 (The Pile)

Max Activating Token Index: 1003